Free health AI: drug interaction checks, medicine facts and health questions in 90+ languages
Scored across 3 tools
ask_health_ai is a broad catch-all that explicitly mentions interactions and medicine details, which overlaps somewhat with check_drug_interaction and medicine_info. However, the specialized tools have clearly scoped inputs and outputs, so an agent can generally choose correctly.
ask_health_ai and check_drug_interaction follow a verb_noun pattern, while medicine_info uses a noun_noun pattern. The mix is minor and all names are descriptive snake_case, so the set remains predictable and readable.
Three tools is a small but well-scoped set for a focused read-only health assistant: a general Q&A tool, a drug interaction checker, and a medicine lookup. Each tool serves a distinct core user need without feeling padded.
The core consumer health workflows are covered: ask questions, check interactions, and look up medicines. Minor gaps exist such as multi-drug interaction checks, food interactions, or generic-to-brand matching, but ask_health_ai partially compensates for these.
Ask GoDavaii's Advanced Health AI any health question (symptoms, medicines, dosing, interactions, lab results, home remedies) and get a structured answer in the same language as the question. Country-aware: Indian brands and prices for Indian users. Read-only; the question is processed once and not stored.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The health question, in any language |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint=true annotation, the description adds valuable behavioral context: answers are 'in the same language as the question,' the tool is 'Country-aware,' and the question is 'processed once and not stored.' These details meaningfully shape an agent's expectations without contradicting the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, with the core purpose front-loaded and no filler. Each sentence contributes: scope, country-awareness, and privacy/read-only behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter open-ended Q&A tool with no output schema, the description is complete: it defines accepted input, answer characteristics (structured, same-language, country-aware), and privacy behavior. Nothing essential to invoking it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the question parameter already has a clear description. The tool description adds value by giving example question types (symptoms, medicines, dosing, interactions, lab results, home remedies) and explaining the same-language behavior, which helps the agent construct an appropriate question.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description opens with a specific verb and resource: 'Ask GoDavaii's Advanced Health AI any health question' and lists concrete categories (symptoms, medicines, dosing, interactions, lab results, home remedies). It is clear, but it does not explicitly contrast with the sibling tools check_drug_interaction and medicine_info, so it misses the full sibling-differentiation bar.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'any health question' implies this is the general-purpose tool, and the enumerated categories signal breadth. However, there is no explicit guidance on when to prefer a sibling (e.g., check_drug_interaction) instead, nor any exclusions, leaving routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether two medicines interact, using GoDavaii's database of 93,000+ verified drug pairs. Accepts generic names (paracetamol, ibuprofen) or Indian brand names (Dolo 650, Combiflam). Returns severity, whether they can usually be taken together, the mechanism, precautions and a link to the full page. Read-only; no data is stored.
| Name | Required | Description | Default |
|---|---|---|---|
| drug1 | Yes | First medicine, generic or Indian brand name | |
| drug2 | Yes | Second medicine, generic or Indian brand name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description's read-only claim is consistent. It adds value by specifying that no data is stored, which is beyond the annotations, but does not elaborate on other behaviors like rate limits or query limitations. The description does not contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with the main purpose, then adds relevant input details and output summary. It is a single sentence that earns its place without excess. Minor improvement could be to separate the return details, but it's already well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter, read-only tool with full schema coverage and no nested objects, the description is quite complete. It covers usage, inputs, output, and safety. It lacks some behavioral specifics like pagination or result limits, but these are unlikely given the nature of the tool. The presence of output details (severity, precautions) compensates for the lack of output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so both parameters are well-documented in the schema. The description adds the useful detail that names can be generic or Indian brand, which is slightly more specific than the schema's description. However, it does not go beyond that, which is acceptable given high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('check drug interaction') and resource (GoDavaii's database of 93,000+ drug pairs), and clearly differentiates from siblings by mentioning the database and read-only nature. It also specifies accepted inputs (generic names and Indian brand names), which is distinct from medicine_info.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides clear context for when to use the tool (checking interactions between two medicines), and implies its role relative to siblings by being read-only and focused. It does not explicitly state when not to use it or why not to use an alternative, but the context is enough for an agent to decide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up an Indian medicine by brand or product name (e.g. Dolo 650, Crocin, Augmentin 625) and get its composition, category, company and reference price in INR, plus the GoDavaii page with uses, side effects and alternatives. Read-only; no data is stored.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Brand or product name as sold in India |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the core safety profile is covered. The description adds 'no data is stored' which is a small privacy note beyond the annotations, but it doesn't disclose any other behavioral traits (e.g., rate limits, error behavior, or response format nuances). It is consistent with annotations, but adds limited extra value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, information-dense sentence. It front-loads the action and resource, provides examples, enumerates return fields, and includes the read-only note—all without any filler or redundancy. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only one input, no output schema, and strong annotations, the description does well: it states exact return fields and the GoDavaii page, and notes read-only behavior. The only gaps are edge-case handling (e.g., not-found medicine, loose brand matching) and whether the output is structured vs. prose, but these are minor for a simple lookup tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% because the input `name` has a description ('Brand or product name as sold in India'), fulfilling the baseline of 3. The description adds concrete examples (Dolo 650, Crocin, Augmentin 625) and the 'Indian medicine' context, which helps an agent pick valid values beyond the schema's generic description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb ('look up') and resource ('Indian medicine by brand or product name'), lists the exact fields returned (composition, category, company, reference price, GoDavaii page with uses/side effects/alternatives), and gives concrete examples. This clearly distinguishes it from siblings like ask_health_ai (general Q&A) and check_drug_interaction (interaction checking).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage: if you need Indian medicine brand/product facts, use this tool. However, it never explicitly contrasts with ask_health_ai or check_drug_interaction, nor says when not to use it. The context makes the intended use reasonably clear, but there is no explicit routing or exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
ask_health_aicheck_drug_interactionmedicine_infoMedical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Drug-drug interaction checker for clinical LLMs using RxNorm and DailyMed.
US Rx prices by pharmacy near you + free discount card; foreign-brand equivalents; 12 languages
Add one secure layer between your agents and this server.
